auto-paper-demo
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches markdown content from AlphaXiv's official endpoints using curl to gather research paper data.
- [COMMAND_EXECUTION]: Uses shell-based curl commands to retrieve remote markdown resources for processing.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external website and uses it as context to generate executable marimo notebook cells and widgets.
- Ingestion points: Paper overviews and full text are fetched from alphaxiv.org as specified in SKILL.md.
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to prevent the agent from following instructions embedded within the paper text.
- Capability inventory: The skill generates Python code for marimo notebooks and JavaScript code for anywidget components as described in SKILL.md and references/ANYWIDGET.md.
- Sanitization: Absent. There are no steps provided to sanitize or validate the external content before it is interpolated into code generation prompts.
Audit Metadata